https://amatria.in/blog/ageofdata The end of the “Age of Data”? Enter the age of superhuman data and AIXavier AmatriainDecember 24, 2024 “This post will argue that the age of data is farContinue readingWhat I Read: Age of Data
https://lilianweng.github.io/posts/2024-11-28-reward-hacking Reward Hacking in Reinforcement LearningLilian WengNovember 28, 2024 “Reward hacking occurs when a reinforcement learning (RL) agent exploits flaws or ambiguities in the reward function to achieve high rewards,Continue readingWhat I Read: Reward Hacking
Debate May Help AI Models Converge on Truth Debate May Help AI Models Converge on TruthStephen OrnesNovember 8, 2024 “Letting AI systems argue with each other may help expose whenContinue readingWhat I Read: Debate, AI
https://magazine.sebastianraschka.com/p/new-llm-pre-training-and-post-training New LLM Pre-training and Post-training ParadigmsA Look at How Modern LLMs Are TrainedSebastian Raschka, PhDAug 17, 2024 “Initially, the LLM training process focused solely on pre-training, but it hasContinue readingWhat I Read: LLM Pre-training Post-training
https://www.anthropic.com/index/evaluating-ai-systems Challenges in evaluating AI systemsOct 4, 2023 “…what many people working inside and outside of AI don’t fully appreciate is how difficult it is to build robust and reliableContinue readingWhat I Read: evaluating AI systems